121 lines
4.6 KiB
JavaScript
121 lines
4.6 KiB
JavaScript
"use strict";
|
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
exports.CheerioWebBaseLoader = void 0;
|
|
const documents_1 = require("@langchain/core/documents");
|
|
const async_caller_1 = require("@langchain/core/utils/async_caller");
|
|
const base_1 = require("@langchain/core/document_loaders/base");
|
|
/**
|
|
* A class that extends the BaseDocumentLoader and implements the
|
|
* DocumentLoader interface. It represents a document loader for loading
|
|
* web-based documents using Cheerio.
|
|
* @example
|
|
* ```typescript
|
|
* const loader = new CheerioWebBaseLoader("https:exampleurl.com");
|
|
* const docs = await loader.load();
|
|
* console.log({ docs });
|
|
* ```
|
|
*/
|
|
class CheerioWebBaseLoader extends base_1.BaseDocumentLoader {
|
|
constructor(webPath, fields) {
|
|
super();
|
|
Object.defineProperty(this, "webPath", {
|
|
enumerable: true,
|
|
configurable: true,
|
|
writable: true,
|
|
value: webPath
|
|
});
|
|
Object.defineProperty(this, "timeout", {
|
|
enumerable: true,
|
|
configurable: true,
|
|
writable: true,
|
|
value: void 0
|
|
});
|
|
Object.defineProperty(this, "caller", {
|
|
enumerable: true,
|
|
configurable: true,
|
|
writable: true,
|
|
value: void 0
|
|
});
|
|
Object.defineProperty(this, "selector", {
|
|
enumerable: true,
|
|
configurable: true,
|
|
writable: true,
|
|
value: void 0
|
|
});
|
|
Object.defineProperty(this, "textDecoder", {
|
|
enumerable: true,
|
|
configurable: true,
|
|
writable: true,
|
|
value: void 0
|
|
});
|
|
Object.defineProperty(this, "headers", {
|
|
enumerable: true,
|
|
configurable: true,
|
|
writable: true,
|
|
value: void 0
|
|
});
|
|
const { timeout, selector, textDecoder, headers, ...rest } = fields ?? {};
|
|
this.timeout = timeout ?? 10000;
|
|
this.caller = new async_caller_1.AsyncCaller(rest);
|
|
this.selector = selector ?? "body";
|
|
this.textDecoder = textDecoder;
|
|
this.headers = headers;
|
|
}
|
|
/**
|
|
* Fetches web documents from the given array of URLs and loads them using Cheerio.
|
|
* It returns an array of CheerioAPI instances.
|
|
* @param urls An array of URLs to fetch and load.
|
|
* @returns A Promise that resolves to an array of CheerioAPI instances.
|
|
*/
|
|
static async scrapeAll(urls, caller, timeout, textDecoder, options) {
|
|
return Promise.all(urls.map((url) => CheerioWebBaseLoader._scrape(url, caller, timeout, textDecoder, options)));
|
|
}
|
|
static async _scrape(url, caller, timeout, textDecoder, options) {
|
|
const { headers, ...cheerioOptions } = options ?? {};
|
|
const { load } = await CheerioWebBaseLoader.imports();
|
|
const response = await caller.call(fetch, url, {
|
|
signal: timeout ? AbortSignal.timeout(timeout) : undefined,
|
|
headers,
|
|
});
|
|
const html = textDecoder?.decode(await response.arrayBuffer()) ??
|
|
(await response.text());
|
|
return load(html, cheerioOptions);
|
|
}
|
|
/**
|
|
* Fetches the web document from the webPath and loads it using Cheerio.
|
|
* It returns a CheerioAPI instance.
|
|
* @returns A Promise that resolves to a CheerioAPI instance.
|
|
*/
|
|
async scrape() {
|
|
const options = { headers: this.headers };
|
|
return CheerioWebBaseLoader._scrape(this.webPath, this.caller, this.timeout, this.textDecoder, options);
|
|
}
|
|
/**
|
|
* Extracts the text content from the loaded document using the selector
|
|
* and creates a Document instance with the extracted text and metadata.
|
|
* It returns an array of Document instances.
|
|
* @returns A Promise that resolves to an array of Document instances.
|
|
*/
|
|
async load() {
|
|
const $ = await this.scrape();
|
|
const text = $(this.selector).text();
|
|
const metadata = { source: this.webPath };
|
|
return [new documents_1.Document({ pageContent: text, metadata })];
|
|
}
|
|
/**
|
|
* A static method that dynamically imports the Cheerio library and
|
|
* returns the load function. If the import fails, it throws an error.
|
|
* @returns A Promise that resolves to an object containing the load function from the Cheerio library.
|
|
*/
|
|
static async imports() {
|
|
try {
|
|
const { load } = await import("cheerio");
|
|
return { load };
|
|
}
|
|
catch (e) {
|
|
console.error(e);
|
|
throw new Error("Please install cheerio as a dependency with, e.g. `yarn add cheerio`");
|
|
}
|
|
}
|
|
}
|
|
exports.CheerioWebBaseLoader = CheerioWebBaseLoader;
|